An extrapolative machine learning framework for forecasting nitrogen oxide mitigation in alcohol enhanced ammonia-methane blends

As carbon-free energy carrier, combustion of ammonia suffers from low burning rates, poor flame stability, and excessive nitrogen oxide (NOx) emissions. Although blending with hydrocarbon fuels such as methane alleviates some drawbacks, NOx formation remains a critical barrier. To address these challenges, we propose a hybrid framework combining reactive force field molecular dynamics (ReaxFF-MD) simulations with machine learning (ML). MD simulations at 2000-3000 K were performed for ammonia-methane blended combustion with 0-10% addition of ethanol or methanol. Adding alcohols suppressed the NOx formation by altering charge redistributions and redirecting nitrogen intermediates into stabilising pathways. Particularly at 3000 K, 10% ethanol and methanol reduced NOx by ∼39.5% and ∼30.1%, respectively. Both chemical and physical descriptors derived from MD were used to train ML models and successfully predicted NOx trends at intermediate compositions (2%, 7%, 12%) with <5% error for ethanol-rich mixtures, though predictions beyond 12% require further validation. This framework reduces reliance on costly simulations while providing mechanistic insights and predictive capability of designing alternative fuels.